paper-with-me

홈 › Papers

ImageFolder: Autoregressive Image Generation with Folded Tokens

2024-10-02 · Xiang Li, Kai Qiu, Hao Chen, Jason Kuen, Jiuxiang Gu, Bhiksha Raj, Zhe Lin

Image tokenizers are crucial for visual generative models, e.g., diffusion models (DMs) and autoregressive (AR) models, as they construct the latent representation for modeling. Increasing token length is a common approach to improve the image reconstruction quality. However, tokenizers with longer token lengths are not guaranteed to achieve better generation quality. There exists a trade-off between reconstruction and generation quality regarding token length. In this paper, we investigate the impact of token length on both image reconstruction and generation and provide a flexible solution to the tradeoff. We propose ImageFolder, a semantic tokenizer that provides spatially aligned image tokens that can be folded during autoregressive modeling to improve both generation efficiency and quality. To enhance the representative capability without increasing token length, we leverage dual-branch product quantization to capture different contexts of images. Specifically, semantic regularization is introduced in one branch to encourage compacted semantic information while another branch is designed to capture the remaining pixel-level details. Extensive experiments demonstrate the superior quality of image generation and shorter token length with ImageFolder tokenizer.

📄 PDF Abstract BibTeX arXiv:2410.01756

Code (1)

lxa9867/imagefolder 공식 구현 pytorch

Tasks

Image GenerationImage ReconstructionQuantization

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Robust Latent Matters: Boosting Image Generation with Sampling Error

2025-03-11 · Kai Qiu, Xiang Li, Jason Kuen, Hao Chen 외

Recent image generation schemes typically capture image distribution in a pre-constructed latent space relying on a frozen image tokenizer. Though the performance of tokenizer plays an essential role to the successful ge…

BenchmarkingImage Generation

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

2025-08-14 · NextStep Team, Chunrui Han, Guopeng Li, Jingwei Wu 외 arxiv

Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discret…

Text-to-Image GenerationImage Editing

SpectralAR: Spectral Autoregressive Visual Generation

2025-06-12 · Yuanhui Huang, Weiliang Chen, Wenzhao Zheng, Yueqi Duan 외

Autoregressive visual generation has garnered increasing attention due to its scalability and compatibility with other modalities compared with diffusion models. Most existing methods construct visual sequences as spatia…

Image Reconstruction

Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots

2025-05-26 · Guangting Zheng, Yehao Li, Yingwei Pan, Jiajun Deng 외

Autoregressive models have emerged as a powerful generative paradigm for visual generation. The current de-facto standard of next token prediction commonly operates over a single-scale sequence of dense image tokens, and…

Image GenerationText to Image GenerationText-to-Image Generation

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis

2025-07-02 · Peng Zheng, Junke Wang, Yi Chang, Yizhou Yu 외

Recent advances in large language models (LLMs) have spurred interests in encoding images as discrete tokens and leveraging autoregressive (AR) frameworks for visual generation. However, the quantization process in AR-ba…

Density EstimationImage GenerationQuantization